Sora 2

Name: Sora 2
Author: OpenAI

openai/sora-2/image-to-video

Sora 2 is OpenAI's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Use in agent Get API key

Base price: $0.40USD / run
Execution: async
Model type: video
Input fields: 5

Try the model

Playground

Open playground

Input

Prompt(string)

The text prompt describing the video you want to generate

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

The URL of the image to use as the first frame

This field is required.

Resolution(string)

The resolution of the generated video Allowed values: auto, 720p.

Duration(integer)

Duration of the generated video in seconds Allowed values: 4, 8, 12, 16, 20.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $0.40 / run
Billing formula: params.duration * 0.10

Context & modalities

Input: Schema-defined
Output: video

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: OpenAI
Model ID: openai/sora-2/image-to-video
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Sora 2 Image To Video

Sora 2 Image To Video is built for cinematic video generation, with this exact route focused on source-image animation. Sora 2 is OpenAI's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output. It is designed for production workflows that need a clearly scoped media operation instead of a generic assistant response, preserving the supplied direction while returning an artifact ready for review, iteration, or downstream assembly.

The request surface keeps creative direction and delivery choices explicit through prompt, duration, image_url, sync_mode, resolution, aspect_ratio. Teams can lock source material, describe the intended result, choose supported output controls, and rerun the same request structure across variations. This makes experiments easier to compare and larger pipelines easier to operate without hiding important decisions inside an opaque preset.

Highlights

Source-Image Animation. The openai/sora-2/image-to-video route is dedicated to source-image animation, keeping inputs and outputs matched to this operation.
Coherent Motion And Scene Continuity. Within openai/sora-2/image-to-video, documented prompt and media controls direct coherent motion and scene continuity while keeping the brief close to the result.
Directable Visual Storytelling. The openai/sora-2/image-to-video result provides directable visual storytelling in a machine-consumable form for review and downstream production.
Route-specific control. For openai/sora-2/image-to-video, documented controls include prompt, duration, image_url, sync_mode, resolution, aspect_ratio, defining the supported variation space for this exact route.

Pricing

Configuration	Price
4 seconds	`$0.4000`
8 seconds	`$0.8000`
12 seconds	`$1.2000`
16 seconds	`$1.6000`
20 seconds	`$2.0000`
Base-price example	`$0.4000`
Rate	`$0.1 per second`

When to Use

Scenario	Why it fits
Choose this route	When the deliverable is specifically source-image animation, not a neighboring generation or editing task.
Production iteration	When creative teams need repeatable coherent motion and scene continuity with an explicit request payload.
Automated pipelines	When directable visual storytelling must flow into review, storage, compositing, or publishing.
Controlled variations	When a stable brief should be rerun while changing only documented inputs.
Prototype to scale	When the same `openai/sora-2/image-to-video` contract should serve a single experiment and a larger batch later.

Prompt Guide

Lead with the subject or source, then state the transformation, important spatial or temporal details, style, and finish. Supply only documented fields, keep media URLs reachable, and vary one control at a time when comparing outputs.

{
  "prompt": "A directed creative request with subject, setting, style, motion, and finish.",
  "image": "https://example.com/reference.jpg"
}

Technical Specs

Property	Value
Model ID	`openai/sora-2/image-to-video`
Required inputs	`prompt`
`prompt`	string
`duration`	integer; options: 4, 8, 12, 16, 20; default: 4
`image_url`	string
`sync_mode`	boolean; default: false
`resolution`	string; options: auto, 720p; default: auto
`aspect_ratio`	string; options: auto, 9:16, 16:9; default: auto
`delete_video`	boolean; default: true
`character_ids`	array
`safety_tolerance`	string; default: 6
`detect_and_block_ip`	boolean; default: false

Related Models

openai/sora-2/characters

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

openai/sora-2/image-to-video

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "openai/sora-2/image-to-video",
  "image": "https://static.sandbase.ai/examples/openai/sora-2/image-to-video/input_image_0.png",
  "prompt": "Front-facing 'invisible' action-cam on a skydiver in freefall above bright clouds; camera locked on his face. He speaks over the wind with clear lipsync: 'This is insanely fun! You've got to try it—book a tandem and go!' Natural wind roar, voice close-mic'd and slightly compressed so it's intelligible. Midday sun, goggles and jumpsuit flutter, altimeter visible, parachute rig on shoulders. Energetic but stable framing with subtle shake; brief horizon roll. End on first tug of canopy and wind noise dropping.",
  "duration": 4,
  "resolution": "auto"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models

Model	Context	Input / 1M	Output / 1M	Released
Sora 2This model `OpenAI`	—	—	—	Oct 6, 2025
Sora 2 Characters `OpenAI`	—	—	—	Mar 12, 2026
Sora 2 Remix `OpenAI`	—	—	—	Oct 8, 2025
Sora 2 Image to Video Pro `OpenAI`	—	—	—	Oct 6, 2025
Sora 2 Text to Video Pro `OpenAI`	—	—	—	Oct 6, 2025
Sora 2 `OpenAI`	—	—	—	Oct 6, 2025